Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    independent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.68
    ScopeManager
    -0.58
     spéciales
    -0.56
     extérieures
    -0.56
     cortas
    -0.55
    TSCA
    -0.54
     cavitation
    -0.53
     passés
    -0.53
    ksis
    -0.53
    cessite
    -0.53
    POSITIVE LOGITS
     Sion
    0.59
    بوابة
    0.53
     IBOutlet
    0.52
    :+:
    0.52
    arXiv
    0.50
     незавершена
    0.50
     ModelExpression
    0.48
     ProtoMessage
    0.47
    fins
    0.47
    PerformLayout
    0.47
    Act Density 0.006%

    No Known Activations